Products
-
Run, Test, and Evaluate Models and MCP Locally with Docker + Promptfoo
Learn how promptfoo and Docker help developers compare models, evaluate MCP servers, and even perform LLM red-teaming.
Read now
-
MCP Horror Stories: The Drive-By Localhost Breach
Learn how CVE-2025-49596 has turned MCP Inspector into a weapon of mass developer environment compromise in this edition of MCP Horror Stories.
Read now
-
Silent Component Updates & Redesigned Update Experience
Automatic updates for Docker Compose, Docker Scout, Ask Gordon, and Model Runner—plus a new update experience and admin controls in Docker Desktop 4.46.
Read now
-
Build and Distribute AI Agents and Workflows with cagent
cagent is a new open-source project from Docker that makes it simple to build, run, and share AI agents, without writing a single line of code. Instead of writing code and wrangling Python versions and dependencies when creating AI agents, you define your agent’s behavior, tools, and persona in a single YAML file, making it…
Read now
-
Docker Model Runner General Availability
Docker Model Runner offers a new way for developers to manage, run, and share local AI models with cutting-edge features and more on the way.
Read now
-
How to Build Secure AI Coding Agents with Cerebras and Docker Compose
Learn how to build a secure, portable AI coding agent with Docker Compose, MCP Gateway, and Cerebras Cloud—plus a no-network code sandbox using Testcontainers
Read now
-
MCP Security: A Developer’s Guide
MCP security refers to the controls and risks that govern how agents discover, connect to, and execute MCP servers.
Read now
-
From Hallucinations to Prompt Injection: Securing AI Workflows at Runtime
Stop LLM mishaps before production. Secure AI agents at runtime with Docker Desktop, Docker Scout, hardened images, and policies against prompt injection.
Read now